One of the Greater London Authority’s (GLA) response to the COVID-19 pandemic brings together multiple large-scale and heterogeneous datasets capturing mobility, transportation and traffic activity over the city of London to better understand ‘busyness’ and enable targeted interventions and effective policy-making. As part of that ongoing project1, we describe an early-warning system and introduce an expectation-based scan statistic for networks to help the GLA and Transport for London understand the extent to which populations are following government COVID-19 guidelines. We explicitly treat the case of geographically fixed timeseries data located on a (road) network and primarily focus on monitoring the dynamics across large regions of the capital in addition to the detection and reporting of significant spatio-temporal regions. Our approach extends the Network Based Scan Statistic (NBSS) by making it expectation-based (EBP) and by using stochastic processes for time-series forecasting, we are able to quantify metric uncertainty in both the EBP and NBSS frameworks. We introduce a variant of the metric used in the original EBP model which focuses on identifying space-time regions in which activity is quieter than expected.
Chance Haycock, Edward Thorpe-Woods, James Walsh, Patrick O’Hara, Oscar Giles, Neil Dhir, Theodoros Damoulas. (2020). An Expectation-Based Network Scan Statistic for a COVID-19 Early Warning System. In Workshop on Machine Learning in Public Health, NeurIPS'20.